Engineering is an inherently long-term process. The Artsy engineering team has been around for 7 years, and that's quite a lot of time to get things done. We use software that keeps track of changes over time thanks to source control, but tools like git only help keep track of small passages of time. I want to keep track of events that could take months to ship.

We've been doing a lot of long-term introspection as a team in 2018. Externally, this has been visible through things like opening our docs and creating our engineering principles. I'm expanding on this with an idea that I took from my work in building large open source projects: Highlight docs.

Read on →

As Artsy Engineering grows in 2018, we have so many newcomers looking for context: they want to understand the systems they'll be working in day-to-day. Awesome! But it's not enough to understand the systems themselves, it's often helpful to understand the history of how we ended up where we are.

Frontend web development has changed a lot during Artsy's existence, and it continues to advance at a blistering pace. It's easy to get caught up in the churn of frameworks and languages and tools, so I want to use this post as an opportunity to contextualize each transition that Artsy's web presence has made over the past seven years. We've changed technologies, but we've tried to do so with care and attention. Documenting these decisions is important (and is ideally done contemporaneously), but even with the best documentation, sometimes our own documentation is unclear to us.

In an effort to help contextualize our web frontend (which is open source), this blog post will document the major transitions that Artsy's web presence has made over the past seven years. Let's begin!

Read on →

For what feels like the last 3-6 months, I've been trying to figure out how to know what the commit is for the Docker runtime in Peril. Roughly: every master commit on Peril triggers a Docker image on Docker Hub for the environment in which JavaScript is running. There's a lag between creating the commit, having the image ready on Docker Hub, and Peril using the new image. There's also space for these automated systems to go wrong, so I'd like to be able to be certain in logging.

I've thrown a lot of commits and time every few weeks at this, so now that I've figured it out, I'll give you an idea of what I needed to do to make it work in a micro-post.

Read on →

Hey there! My name is Anson and I work on the Platform team at Artsy. Recently, we faced an issue where a certain Enzyme test we wrote using mock tracking was failing, but we couldn't figure out why. Luckily, with some help from Orta and some clever thinking, we figured out what was going on.

Read on →

The Artsy Engineering team recently underwent the process of defining our guiding principles; you can read through the pull request here and the finished principles here. In this blog post, I'd like to use our experience of defining these to answer the following questions:

  • Why define engineering guiding principles?
  • What makes principles different from company values?
  • How to define guiding principles?

Let's dive in.

Read on →

Artsy is growing up. We have thousands of subscriber galleries paying 3 to 4 figure monthly fees. As we're starting to see a real market-fit, and have started to mature our organization. For example, this year we introduced product managers into our 8 year old company to help us figure out how to build the right things. We actually started having open headcount on Engineering again, for the first time in years.

As a part of maturing, our team has really had to start considering how to make parts of our culture explicit instead of implicit. We have new, awesome folks wanting to understand why things are the way they are as well as folk who are raising up to new responsibilities only to find them completely un-documented.

In-part, having a consistent team for so long hasn't made it worth the time to document things everyone knows, but growth is very happy to disrupt that balance. Now we're shipping documentation updates weekly, to all sorts of places. In trying to write an awesome document, which I'll cover later, I looked at how we had consolidated our documentation over the last few years, and saw that we had fragmented due the tensions around wanting to write publicly.

This post covers that tension, and how we came about to the new docs setup.

Read on →

Programming generally requires getting into a good flow state and working on a tricky problem for some time. In the last 2 years, most of my work at Artsy (and in the OSS world) has been less about longer-term building of hard things, but working on many smaller tasks across a lot of different areas.

Somehow, during this period I managed to end up in the top of "most active" GitHub members, I feel like a lot of this is due to doing Open Source by Default at Artsy and second to being good at context switching. I want to try and talk though some of my techniques for handling context switching, as well as a bit of philosophy around adopting and owning your tools.

Read on →

Hey all, we have another guest post, this one comes from Sibelius Seraphini - a very active contributor to Relay and its eco-system. When we spotted he had wrote an amazing article on how the networking aspects of Relay comes together, we wanted to expand his reach and inform more people on how Relay comes together.

-- Orta

Data fetching is a hard problem for apps. You need to ask yourself a lot of questions: How do you ask for data from a server? How do you handle authentication? When is the right time to request data? How can you ensure you have all the necessary data to render your views? How can you make sure you're not over-fetching? Can you do lazy loading? When should you trigger lazy loading of data? What about pre-fetching data?

Relay is a framework for building data-driven applications which handles data fetching for you. For an introduction to Relay, read their docs, and also check out my Relay talk at React Conf BR.

You don’t deep dive if you don’t know how to swim

TL;DR Relay Modern Network

Relay will aggregate the data requirements (fragments) for your components, then create a request to fulfill it. The API to do this is via the Relay Environment:

The Relay "Environment" bundles together the configuration, cache storage, and network-handling that Relay needs in order to operate.

This post focuses on the "network-handling" part, the Network Layer. The network layer's responsibility is to make a request to a server (or a local graphql) and return the response data to Relay. Your implementation should conform to either FetchFunction for a Promise-like API, or SubscribeFunction for an Observable-like API.

This article will provide 5 implementations of a Relay Network Interface, each of one providing more capabilities than the other one, eventually enabling GraphQL Live Queries and Deferrable Queries.

You can see the code for these 5 network layers on GitHub here, open source under MIT license:

Read on →

We're at 9 months of serious usage of Peril in Artsy. However, I've been worried.

To get you up to speed on Peril, Peril is a tool that takes GitHub webhooks, and makes it easy to build one-off actions. It does this by having a per-account settings JSON, that connects JavaScript files to events from webhooks. So, for example, you can write a rule which runs when closing an issue in GitHub that looks for associated Jira tickets and resolves them. Peril provides no implicit actions like that, it instead offers a JavaScript runtime environment optimised to this domain so you can make actions to fit your needs. Like a collection of single-file probots.

Three months ago I started building out a "true" staging environment for Peril, one that allows any user or org on GitHub to click a button and have Peril running on their account. Pulling this off has two real interesting problems. Problem number one, security. Problem number two, my wallet.

Both of these issues stem from one simple problem: I need to run other people's code on my machines and I think they should be able to store data. Which to be quite frank, is horrifying for a side-project. So, this post explores one of main aspects which I've architected Peril to make this problem tractable. Avoiding storing state in the form of data.

Read on →

Hi! I'm Erik, a software engineer on the Purchase team. One of the most visible payoffs from Artsy's investments in React Native over the past two years has been the opening up of our mobile codebase to contributors like myself coming primarily from web stacks. It's nice to be able to build mobile interfaces with the same declarative API used by so many of our web projects, but sometimes we still need to bridge the divide to our Objective-C and Swift ecosystem. One such case: replacing the app secrets typically loaded from a deploy environment or web developer's dotenv file.

Read on →